Papers › MS MARCO: A Human Generated MAchine Reading COmprehension Dataset

MS MARCO: A Human Generated MAchine Reading COmprehension Dataset

28 Nov 2016arXiv:1611.09268archive 2025-07-28

Payal Bajaj, Daniel Campos, Nick Craswell, Li Deng, Jianfeng Gao, Xiaodong Liu, Rangan Majumder, Andrew McNamara, Bhaskar Mitra, Tri Nguyen, Mir Rosenberg, Xia Song, Alina Stoica, Saurabh Tiwary, Tong Wang

We introduce a large scale MAchine Reading COmprehension dataset, which we name MS MARCO. The dataset comprises of 1,010,916 anonymized questions---sampled from Bing's search query logs---each with a human generated answer and 182,669 completely human rewritten generated answers. In addition, the dataset contains 8,841,823 passages---extracted from 3,563,535 web documents retrieved by Bing---that provide the information necessary for curating the natural language answers. A question in the MS MARCO dataset may have multiple answers or no answers at all. Using this dataset, we propose three different tasks with varying levels of difficulty: (i) predict if a question is answerable given a set of context passages, and extract and synthesize the answer as a human would (ii) generate a well-formed answer (if possible) based on the context passages that can be understood with the question and passage context, and finally (iii) rank a set of retrieved passages given a question. The size of the dataset and the fact that the questions are derived from real user search queries distinguishes MS MARCO from other well-known publicly available datasets for machine reading comprehension and question-answering. We believe that the scale and the real-world nature of this dataset makes it attractive for benchmarking machine reading comprehension and question-answering models.

PaperPDFCodeCode Syntology ran

In Syntology View this paper on Syntology, its page in Syntology's graph. That page adds which of its functions are also present in other papers' code Syntology holds, with dates, and its dated run record as JSON and a README badge. It also lists the repositories linked to the paper, the abstract and the calls for agents.

Open this paper in Syntology's Atlas, the map of the papers in Syntology's graph and their citations.

For agents, on Syntology's MCP service (how to connect):

Code

Syntology 33 code samples harvested from 6 repositories linked to this paper: 28 ran (of which 0 constructed an object rather than computing a result; 23 with no instrument failure: 0 honoured, 0 violated, 23 with no contract checked; 5 where Syntology's instrument failed) · 5 unverified. Where Syntology's instrument failed: 5 where our contract draft was wrong; failures of Syntology's instrument, not of the code.

By repository: community (archive-listed): 33 samples from 6 repositories, 28 ran (23 with no instrument failure; 5 where Syntology's instrument failed). The run record, sample by sample. “Ran” means executed on a synthesized input, not that the code is correct or reproduces the paper.

No sample is linked to this paper from 1 of its repositories that Syntology harvested for other papers:

Levels written between 2026-09-22 and 2026-09-26 (UTC): the dates Syntology's graph wrote each sample's verification level, not when the code executed.

14 repositories listed; official and paper-mentioned ones first.

AmenRa/rank_eval mentioned on GitHubMITSyntology: 5 samples, 3 ran (0 instrument-failed) · 2 unverified report
amenra/ranx mentioned on GitHubMITSyntology: 1 sample, 1 ran (0 instrument-failed) · 0 unverified report
axiomlab/Cable mentioned on GitHubpytorchSyntology: not harvested report
dfcf93/MSMARCO mentioned on GitHubpytorchMITSyntology: 9 samples, 8 ran (0 instrument-failed) · 1 unverified report
microsoft/MSMARCO-Conversational-Search mentioned on GitHubMITSyntology: not harvested report
microsoft/MSMARCO-Document-Ranking mentioned on GitHubCC-BY-4.0Syntology: not harvested report
microsoft/MSMARCO-OpenKP mentioned on GitHubMITSyntology: not harvested report
microsoft/MSMARCO-Passage-Ranking mentioned on GitHubMITSyntology: 6 samples, 5 ran (2 instrument-failed) · 1 unverified report
microsoft/MSMARCO-Question-Answering mentioned on GitHubpytorchMITSyntology: 6 samples, 6 ran (3 instrument-failed) · 0 unverified report
microsoft/OpenKP mentioned on GitHubMITSyntology: 6 samples, 5 ran (0 instrument-failed) · 1 unverified report
microsoft/TREC-2019-Deep-Learning mentioned on GitHubCC-BY-4.0Syntology: not harvested report
princeton-nlp/helmet mentioned on GitHubpytorchMITSyntology: no sample linked to this paper (harvested for another paper). Syntology's graph links these samples to HELMET: How to Evaluate Long-Context Language Models Effectively and Thoroughly (arXiv:2410.02694; that paper's own run record: 6 ran (of which 0 constructed an object rather than computing a result; 1 with no instrument failure: 0 honoured, 0 violated, 1 with no contract checked; 5 where Syntology's instrument failed) · 4 unverified) and ATLAS: All-round Testing of Long-context Abilities across Scales (arXiv:2605.28079; that paper's own run record: 1 ran (of which 1 constructed an object rather than computing a result; 1 with no instrument failure: 0 honoured, 0 violated, 1 with no contract checked; 0 where Syntology's instrument failed) · 0 unverified; the one sample that ran constructed an object rather than computing a result); nothing checks that they implement this paper's method. report
yongbowin/MSMARCO-Question-Answering_annotation mentioned on GitHubpytorchMITSyntology: not harvested report
yongbowin/OpenKP_annotation mentioned on GitHubMITSyntology: not harvested report

Repository list and official/mentioned flags are the archive's, frozen 2025-07-28. Reachability, where shown, is from one Syntology probe window (2026-09-16 to 2026-09-18); repositories not probed show nothing. GitHub stars are not tracked.

A paper named beside a repository with no sample linked to this paper is shown with that paper's own run record, not this paper's: “ran” means executed on a synthesized input, not that the code is correct, and “where Syntology's instrument failed” counts failures of Syntology's instrument, not of the code. Papers are listed in arXiv-id order, at most three per repository.

Code Syntology ran Syntology

33 samples harvested: 28 ran (of which 0 constructed an object rather than computing a result; 23 with no instrument failure: 0 honoured, 0 violated, 23 with no contract checked; 5 where Syntology's instrument failed) · 5 unverified. “Where Syntology's instrument failed” counts failures of Syntology's instrument, not of the code. Syntology's record for this page last changed ; when this build read Syntology's graph is in the build record. That date is not when the samples ran.

5ran · our draft was wrong
23ran
5unverified

Licence: 0 of the 33 samples are pointer only, meaning Syntology does not serve that copy's text. This page shows no code text for any sample; each one links to its file in the repository.

Harvested from 6 repositories linked to this paper, official or community; the list below is grouped by repository, each group headed by its name and what it is to the paper. “Ran” means the sample executed on a synthesized input. It does not mean the output is correct, and nothing here reproduces the paper's results. A line beginning “fixture:” under a sample that ran gives the arguments Syntology's fixture called the sample with, each as name:type/rank/element kind (? where none was recorded), and the type of what the fixture's run returned, exactly as the harness recorded them; the arguments and the returned type were recorded by two separate runs of the same fixture. No output value is shown, and a returned type says nothing about whether the output was right. “Level recorded” gives the UTC date when Syntology's graph wrote the sample's verification level, not when the code executed; where the level was written before Syntology's graph kept that date, the row says “level recorded, date not recorded”. “Honoured” and “violated” refer to a contract Syntology drafted from the code itself. “Our draft was wrong” and “the contract check could not run” are failures of Syntology's instrument, not of the code: the sample ran on Syntology's synthesized input, and then the drafted contract did not describe it, or the check itself raised an error (RAISES), lacked a dependency (DEP_MISSING) or ran out of time (TIMEOUT); hover the label for which. A metamorphic tier, where shown, is evidence of the output's shape, not that the sample implements the method.

Each sample ends with its code_sha256. A sample's code_sha256 is Syntology's identity for that exact code. It is printed in full (16 hexadecimal characters for every sample in this build), and get_code(code_sha256="…") takes it exactly as printed. An agent calls it on Syntology's MCP service (how to connect); click an identity to copy that call.

Repository labels, per sample. official repository: The archive marks this repository official for the paper. named in the paper: The archive records that the paper mentions this repository; it is not marked official. community (archive-listed): In the archive's code links for this paper, not marked official and not recorded as mentioned in the paper. found in paper text by Syntology: Syntology found this repository in the paper's own text; whether it is the authors' implementation is not asserted. community: Not in the archive's code links for this paper; a community repository Syntology harvested. Samples are grouped by repository: a repository marked official first, then by how directly the repository is tied to the paper, then in the archive's order; never by how many ran. Licence labels name the repository's licence as recorded at harvest. “Pointer only” means Syntology does not serve that copy's text, for one of six reasons: no licence file was found; the licence was not identified; the licence is recorded as permissive but that copy's record is not marked cleared; the licence is outside the permissive list Syntology serves text under (MIT, Apache-2.0, BSD and similar); this paper's copy was not located, so its licence is not recorded; or this paper's copy is cleared, but the stored copy of the same code that Syntology serves is not. Some licences outside that list permit redistribution, such as WTFPL, and GPL-3.0 under its conditions; they are simply not on the list. Hover a licence label for the reason. File links open the file on GitHub at the default branch, which may have changed since the harvest.

A function or class name links to its page when the name occurs in the harvested code of at least 5 papers; the name is a string, not an identity.

AmenRa/rank_eval community (archive-listed) 5 samples, 3 ran (0 instrument-failed) · 2 unverified
get_file_kind ranx/data_structures/qrels.py ran MIT (permissive) · 77f6de2e73ca8660 · report fixture: signature path:str/0/str, kind:NoneType/0/? · returned str · level recorded 2026-09-26
get_metric_label ranx/ranxhub.py ran MIT (permissive) · ec8c6814aa969fd2 · report fixture: signature m:str/0/str · returned str · level recorded 2026-09-26
get_url in 8 papers ranx/io.py ran fingerprinted MIT (permissive) · 76ec290b848f6d2d · report fixture: signature id:str/0/str · returned str · level recorded 2026-09-26
get_path in 30 papers ranx/io.py unverified MIT (permissive) · cdbcc024a7240d33 · report
get_tmp_path ranx/io.py unverified MIT (permissive) · 036a6050bf6f5374 · report
amenra/ranx community (archive-listed) 1 sample, 1 ran (0 instrument-failed) · 0 unverified
get_candidates in 12 papers ranx/fusion/bordafuse.py ran MIT (permissive) · ccb4d73aaca976aa · report fixture: signature runs:list/1/dict · returned List · level recorded 2026-09-26
dfcf93/MSMARCO community (archive-listed) 9 samples, 8 ran (0 instrument-failed) · 1 unverified
generateOuput ConversationalSearch/generateQueryEmbeddings.py ran MIT (permissive) · 537a8f2a5574b5d6 · report fixture: signature responses:list/1/dict · returned str · level recorded 2026-09-26
loadMSMARCO ConversationalSearch/generateQuerysets.py ran MIT (permissive) · 19ad04a1d7cd706f · report fixture: signature files:list/1/str · returned set · level recorded 2026-09-26
loadNQ ConversationalSearch/generateQuerysets.py ran MIT (permissive) · f35b559c8eea08c7 · report fixture: signature dirPath:str/0/str · returned set · level recorded 2026-09-26
loadQueries ConversationalSearch/generateArtificialSessions.py ran MIT (permissive) · 31374e7d57fb5faa · report fixture: signature filename:str/0/str · returned set · level recorded 2026-09-26
loadQueries ConversationalSearch/generateQueryEmbeddings.py ran MIT (permissive) · f65721714fdad34b · report fixture: signature filename:str/0/str · returned list · level recorded 2026-09-26
loadSessions ConversationalSearch/generateArtificialSessions.py ran MIT (permissive) · daf613df77edb1b0 · report fixture: signature filename:str/0/str · returned list · level recorded 2026-09-26
loadVectors ConversationalSearch/generateArtificialSessions.py ran MIT (permissive) · 695af7f11d756cdd · report fixture: signature filename:str/0/str, realQueries:list/1/str, artificialQueries:list/1/str · returned tuple · level recorded 2026-09-26
process in 60 papers ConversationalSearch/generateQueryEmbeddingsBERT.py ran MIT (permissive) · 90cfc8bb296d7674 · report fixture: signature queryPack:list/1/str, response:list/1/list · returned str · level recorded 2026-09-26
loadQuora ConversationalSearch/generateQuerysets.py unverified MIT (permissive) · 16d3a24b2a035ad7 · report
microsoft/MSMARCO-Passage-Ranking community (archive-listed) 6 samples, 5 ran (2 instrument-failed) · 1 unverified
loadPassages generateBERTPassageEmbedding.py ran MIT (permissive) · 4aae25f3615c1cb4 · report fixture: signature filename:str/0/str · returned dict · level recorded 2026-09-25
load_candidate_from_stream in 7 papers ms_marco_eval.py ran · our draft was wrong MIT (permissive) · 44dabd5275dfdd74 · report fixture: signature f:StringIO/0/? · returned dict · level recorded 2026-09-24
load_reference_from_stream in 7 papers ms_marco_eval.py ran · our draft was wrong MIT (permissive) · b09cad901d138056 · report fixture: signature f:StringIO/0/? · returned dict · level recorded 2026-09-24
process in 60 papers generateBERTPassageEmbedding.py ran MIT (permissive) · ab7871c7af226530 · report fixture: signature passageIDs:list/1/str, response:list/1/list · returned str · level recorded 2026-09-25
remove_empty getstats.py ran MIT (permissive) · 6f73ec516845e330 · report fixture: signature a_list:list/1/list · returned list · level recorded 2026-09-25
load_reference in 9 papers ms_marco_eval.py unverified MIT (permissive) · 52e247dd5467b4bb · report
microsoft/MSMARCO-Question-Answering community (archive-listed) 6 samples, 6 ran (3 instrument-failed) · 0 unverified
cook_refs in 36 papers Evaluation/bleu_scorer.py ran · our draft was wrong MIT (permissive) · 7586e1d32f7325f7 · report fixture: signature refs:list/1/str, eff:str/0/str, n:int/0/int · returned tuple · level recorded 2026-09-25
cook_test in 35 papers Evaluation/bleu_scorer.py ran · our draft was wrong MIT (permissive) · 019ae8bc6f98133f · report fixture: signature test:str/0/str, xxx_todo_changeme:tuple/1/list, eff:NoneType/0/?, n:int/0/int · returned dict · level recorded 2026-09-25
get_stats in 37 papers Utils/get_stats_about_length.py ran MIT (permissive) · 9346371b965cc92e · report fixture: signature histogram:dict/0/? · returned float · level recorded 2026-09-26
precook in 38 papers Evaluation/bleu_scorer.py ran · our draft was wrong fingerprinted MIT (permissive) · ec4448373d72d636 · report fixture: signature s:str/0/str, n:int/0/int, out:bool/0/bool · returned tuple · level recorded 2026-09-22
remove_punctuation in 14 papers Evaluation/eval_exp.py ran fingerprinted MIT (permissive) · 0a2e4a7e57b0e25a · report fixture: signature text:str/0/str · returned str · level recorded 2026-09-26
whether_ynq Utils/exploredata.py ran MIT (permissive) · 5b99609663c1da5c · report fixture: signature query:str/0/str · returned bool · level recorded 2026-09-26
microsoft/OpenKP community (archive-listed) 6 samples, 5 ran (0 instrument-failed) · 1 unverified
dedup evaluate.py ran fingerprinted MIT (permissive) · 2a9560b1d7891c67 · report fixture: signature kp_list:list/1/tuple · returned list · level recorded 2026-09-25
getScoreEM agreement.py ran fingerprinted MIT (permissive) · 5bbdf43246de0b42 · report fixture: signature candidate:list/1/str, gold:list/1/str · returned float · level recorded 2026-09-25
getScoreUnigram agreement.py ran MIT (permissive) · 1789c669f2709136 · report fixture: signature candidate:list/1/frozenset, gold:list/1/frozenset · returned float · level recorded 2026-09-25
normalize_answer in 304 papers evaluate.py ran fingerprinted MIT (permissive) · ae96a7f4fe58827f · report fixture: signature s:str/0/str · returned str · level recorded 2026-09-25
remove_empty evaluate.py ran MIT (permissive) · 113dbc7ab532d6a3 · report fixture: signature a_list:list/1/str · returned list · level recorded 2026-09-25
loadJudgements agreement.py unverified MIT (permissive) · 2e000671b39ad111 · report

Tasks

BenchmarkingMachine Reading ComprehensionQuestion AnsweringReading Comprehension

Datasets

Introduced by this paper, per the archive.

MS MARCO

Results from the paper archive 2025-07-28

No leaderboard rows for this paper in the archive.

Report a problem or propose a change · a person checks every report against the paper or source before anything changes; decisions are listed on /corrections